AIF-C01
AWS Certified AI Practitioner (AIF-C01) practice questions and study guide
Learn the core ideas of AI, machine learning and generative AI, how foundation models are used, tuned, evaluated, secured and governed on Amazon Web Services, through short lessons that follow the five domains of the AIF-C01 exam. Independent study material. Not affiliated with, sponsored or endorsed by Amazon Web Services. Amazon Web Services, AWS and AWS Certified AI Practitioner are trademarks of Amazon.com, Inc. or its affiliates.
What you will learn
- Explain AI, ML, deep learning, generative AI and agentic AI and pick the right technique for a use case
- Choose foundation models, prompt techniques, RAG, agents and customization approaches for a business need
- Evaluate models with the right metrics and apply responsible AI, transparency and bias practices
- Secure and govern AI workloads with the right AWS services, guardrails and compliance processes
Topics by exam domain
AI and ML basics
The vocabulary of AI, ML, deep learning and GenAI, plus data types, learning types and inferencing options.
AI use cases and AWS AI services
When AI fits, which technique to pick and which managed AWS AI service solves a given problem.
ML lifecycle, MLOps and metrics
The stages of an AI/ML pipeline, how models reach production, MLOps ideas and how to measure model and business success.
Generative AI concepts
Tokens, embeddings, model families, the FM lifecycle, token pricing, context engineering and agentic AI concepts.
GenAI strengths, limits and AWS services
What GenAI is good and bad at, how to pick models and value, and the AWS services and cost tradeoffs for building GenAI apps.
Designing foundation model applications
Model selection criteria, inference parameters, RAG with vector stores, customization cost tradeoffs and AI agents.
Prompt engineering
Prompt constructs, techniques, best practices, risks and versioning prompts with Amazon Bedrock Prompt Management.
Training and fine-tuning foundation models
Pre-training, fine-tuning methods, distillation and how to prepare data for tuning.
Evaluating foundation models
Evaluation approaches, text metrics, business alignment and evaluating RAG, agents and workflows.
Responsible and explainable AI
Features of responsible AI, legal risks, datasets, bias and variance, transparency and explainability.
Securing and governing AI solutions
AWS security services for AI, data origin, secure data practices, prompt injection, grounding, and governance and compliance.
Study all of AIF-C01 in the app
Short lessons, instant explanations and spaced review of what you get wrong. Free on iOS and Android.
